Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search
While generative models have enabled training-free reward alignment, current methods typically excel in local exploration within narrow regions of the underlying distribution. These approaches struggle when preferences are unknown a priori and only revealed through sequential feedback-a scenario demanding broad exploration to uncover high-utility regions. To address this, we propose Sequentially-Controlled Interactive Multi-Particle Flow-Maps (IMPFM), a framework for sample-efficient online feedback-driven search. IMPFM progressively transports a group of interactive particles toward the targe
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownGradient-based Planning for World Models at Longer Horizons →
- LinkedLinked via arxiv author · 85%Binglin Ji →
“Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search”
- LinkedLinked via arxiv author · 85%Anindya Sarkar →
“Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search”
- LinkedLinked via arxiv author · 85%Hengchang Lu →
“Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search”
- LinkedLinked via arxiv author · 85%Jens Sjölund →
“Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search”
- LinkedLinked via arxiv author · 85%Yevgeniy Vorobeychik →
“Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search”